MULTI-AGENT REINFORCEMENT LEARNING FOR COALITIONAL BARGAINING GAMES

Lucia Cipolina-Kun, Stephen Mak, Ignacio Carlucho, Vahid Yazdanpanah, Sebastian Stein, Enrico Gerding, Kalesha Bullard

Keywords: Coalition formation, cooperative MARL, Game Theory

TL;DR: Why is it theoreticaly correct to use MARL for coalition bargaining games? when and how is it principled? what are the benefits and limitations in the use of MARL for coalition bargaining games?

Abstract: In recent years, there has been growing attention to the application of MARL to coalition formation problems, in particular, on coalitional bargaining games as a means of negotiation. However, the lack of theoretical principles for using MARL in coalitional bargaining games remain less explored. This paper aims to address this gap by providing an examination of the theoretical link between coalition formation, coalitional bargaining games, and MARL through the link of stochastic games. Through this analysis, the paper seeks to shed light on the underlying principles that support the use of MARL in coalitional bargaining and to explore the contributions of this approach and its limitations in comparison to traditional game theoretical methods.